Agent Memory Leaderboard Cycle 2 results: MemoraX tops code memory track at 68.00 points
nikola_mr64990 · x · 2026-11-19
Agent Memory Leaderboard (AML) Cycle 2 results are out: 402 task submissions and 292 valid leaderboard entries across three tracks — text, code, and multimodal memory — testing whether AI agents can actually learn from past experience.
Teams came from Alibaba Cloud DMS, Shopee, OPPO, KT, OceanBase, plus universities, memory startups, and independent developers. MemoraX leads the Code Memory Commercial Products ranking with 68.00 points. The benchmark positions memory as a measurable dimension of agent capability.
Related event: Agent Memory Leaderboard Cycle 2 Released, MemoraX Tops Rankings(2 posts)→
More from coding & agent
- Microsoft launches agent controls, a runtime policy control plane for enterprise agents — krishnan · 2026-11-19
- Buyer's checklist: if a self-written agent skill misfires, can you roll back? — krishnan · 2026-11-19
- Nous Research ships Hermes Enterprise with Microsoft, tops OpenRouter at ~2T tokens/day — krishnan · 2026-11-19
- AWS security chief: before giving an AI agent more authority, test how it fails — AccBalanced · 2026-11-19
- Perplexity agent spent $2.20 on API calls to pick the best of 327 land parcels for a 12-cabin build — jeffgrimes9 · 2026-11-19
- How my agent software factories run on Vercel Board: dedicated agent keeps PRs green — cramforce · 2026-11-19